Skip to content

Benchmark

Vals IOI

Coding benchmarks compare models on programming tasks. Scores are percentages.

Models measured
45
Scores recorded
45
Sources
1
IQ weight
2.75

Score distribution

56.8%
Mean
52.5%
Median
24.4%
Std dev
22.8%
10th percentile
91.2%
90th percentile
2.4%
Min
2.4%100%
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.75 for chat models, measured over 45 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard